Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …

Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision …

We present ImageBind, an approach to learn a joint embedding across six different
modalities-images, text, audio, depth, thermal, and IMU data. We show that all combinations …

We propose a simple pairwise sigmoid loss for image-text pre-training. Unlike standard
contrastive learning with softmax normalization, the sigmoid loss operates solely on image …

Abstract We present Fast Language-Image Pre-training (FLIP), a simple and more efficient
method for training CLIP. Our method randomly masks out and removes a large portion of …

Prevalent semantic segmentation solutions, despite their different network designs (FCN
based or attention based) and mask decoding strategies (parametric softmax based or pixel …

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners
for computer vision. Our MAE approach is simple: we mask random patches of the input …

Considering the ill-posed nature, contrastive regularization has been developed for single
image dehazing, introducing the information from negative images as a lower bound …

Federated learning has emerged as an important distributed learning paradigm, which
normally involves collaborative updating with others and local updating on private data …